公开(公告)号：US20140118477A1

公开(公告)日：2014-05-01

申请号：US13661924

申请日：2012-10-26

Applicant: Google Inc.

Inventor： Michael Dodd ,  Rodrigo Carceroni

IPC: H04N7/14

CPC classification number: H04N7/15 ,  G06T3/4092 ,  H04L65/403 ,  H04L65/605 ,  H04N9/67 ,  H04N21/25825 ,  H04N21/2662 ,  H04N21/41407 ,  H04N21/4788

Abstract: Implementations relate to a system for video encoding and conversion including an image resolution conversion component operable to convert a resolution of a source image frame from a first resolution to a second resolution to produce a first intermediate image frame at the second resolution; an image conversion component operable to receive the first intermediate image frame and convert an image size of the first intermediate image frame to another image frame size to produce a first viewable image frame; an image viewer component operable to display the first viewable image on a first display; a color space conversion component comprising a luminance conversion component and a chrominance operable to receive the first viewable image frame and convent a first luminance value and a first chrominance value of the first viewable image frame to a second intermediate image frame having a second luminance value and a second chrominance value.

Abstract translation: 实现涉及用于视频编码和转换的系统，包括可操作以将源图像帧的分辨率从第一分辨率转换为第二分辨率以产生第二分辨率的第一中间图像帧的图像分辨率转换组件; 图像转换部件，用于接收所述第一中间图像帧，并将所述第一中间图像帧的图像尺寸转换为另一图像帧尺寸以产生第一可视图像帧; 图像查看器组件，可操作以在第一显示器上显示第一可视图像; 颜色空间转换组件，包括亮度转换分量和色度，可操作以接收第一可视图像帧并将第一可视图像帧的第一亮度值和第一色度值修改为具有第二亮度值的第二中间图像帧，以及 第二个色度值。

公开(公告)号：US10212338B2

公开(公告)日：2019-02-19

申请号：US15358770

申请日：2016-11-22

Applicant: Google Inc.

Inventor： Rodrigo Carceroni

IPC: H04N5/232 ,  G10L15/22 ,  G10L15/26 ,  G10L15/18 ,  G06K9/00

Abstract: In general, techniques of this disclosure may enable a computing device to capture one or more images based on a natural language user input. The computing device, while operating in an image capture mode, receive an indication of a natural language user input associated with an image capture command. The computing device determines, based on the image capture command, a visual token to be included in one or more images to be captured by the camera. The computing device locates the visual token within an image preview output by the computing device while operating in the image capture mode. The computing device captures one or more images of the visual token.

公开(公告)号：US20170111584A1

公开(公告)日：2017-04-20

申请号：US14883515

申请日：2015-10-14

Applicant: Google Inc.

Inventor： Wei Hong ,  Rodrigo Carceroni

IPC: H04N5/232 ,  G06T5/20 ,  G06T5/10

CPC classification number: H04N5/23248 ,  G06T3/0093 ,  G06T5/003 ,  G06T5/10 ,  G06T5/20 ,  G06T7/246 ,  G06T2207/10016 ,  H04N5/23229 ,  H04N5/23296

Abstract: In general, the subject matter can be embodied in methods, systems, and program products for identifying, by a computing system and using first and second frames of a video, a transformation that indicates movement of a camera with respect to the frames. The computing system generates a modified transformation so that the transformation is less representative of recent movement. The computing system uses the transformation and the modified transformation to generate a second transformation. The computing system identifies an anticipated distortion that would be present in a stabilized version of the second frame. The computing system determines an amount by which to reduce a stabilizing effect. The computing system applies the second transformation to the second frame to stabilize the second frame, where the stabilizing effect has been reduced based on the determined amount by which to reduce the stabilizing effect.

公开(公告)号：US08983193B1

公开(公告)日：2015-03-17

申请号：US13628735

申请日：2012-09-27

Applicant: Google Inc.

Inventor： Vicente Ignacio Ordonez Roman ,  Jennifer Ann Gillenwater ,  Rodrigo Carceroni ,  Amarnag Subramanya ,  Wei Hua ,  Hui Fang

IPC: G06K9/46 ,  G06K9/00

CPC classification number: G06K9/00 ,  G06F17/30247 ,  G06K9/00684 ,  G06K9/6263 ,  G06K9/6277

Abstract: A computer-implemented technique can receive, at a computing device including one or more processors, a plurality of photos. The technique can extract quality features and similarity features for each of the plurality of photos and can obtain weights for the various quality features and similarity features based on an analysis of a reference photo collection. The technique can generate a quality metric for each of the plurality of photos and can generate a similarity matrix for the plurality of photos by analyzing the various quality features and similarity features and using the obtained weights. The technique can perform joint global maximization of photo quality and photo diversity using the quality metrics and the similarity matrix in order to select a subset of the plurality of photos having a high degree of representativeness. The technique can then store the subset of the plurality of photos in a memory.

Abstract translation: 计算机实现的技术可以在包括一个或多个处理器的计算设备处接收多个照片。 该技术可以为多张照片中的每一张照片提取质量特征和相似性特征，并且可以基于参考照片集合的分析来获得各种质量特征和相似性特征的权重。 该技术可以为多个照片中的每一个生成质量度量，并且可以通过分析各种质量特征和相似性特征并使用获得的权重来生成多张照片的相似性矩阵。 该技术可以使用质量度量和相似性矩阵来执行照片质量和照片分集的联合全局最大化，以便选择具有高度代表性的多张照片的子集。 该技术然后可以将多个照片的子集存储在存储器中。

公开(公告)号：US20150074574A1

公开(公告)日：2015-03-12

申请号：US14547078

申请日：2014-11-18

Applicant: Google Inc.

Inventor： Rodrigo Carceroni ,  Pannag Raghunath Sanketi ,  Amarnag Subramanya

IPC: G06F17/30 ,  G06F3/0484 ,  H04N5/232

CPC classification number: G06F17/3028 ,  G06F3/04842 ,  G06K9/6219 ,  G06T11/60 ,  H04N5/23216 ,  H04N5/23293

Abstract: A computer-implemented technique can receive a plurality of photos and automatically select a subset of the plurality of photos having a high degree of representativeness by jointly maximizing both photo quality and photo diversity to obtain a photo album. The technique can determine one or more clusters for the photo album using a hierarchical clustering algorithm, and store the photo album according to the one or more clusters. The technique can control the manner in which the photo album is displayed using the one or more clusters. The technique can adjust at least one of the one or more clusters and the automatic photo album generation based on user input. The user input can include at least one of adding, deleting, and moving a photo with respect to the one or more clusters. The technique can then re-cluster, automatically generate a new photo album, and/or adjust the presentation.

Abstract translation: 计算机实现的技术可以接收多张照片，并通过联合最大化照片质量和照片分集来获得相册，自动选择具有高度代表性的多张照片的子集。 该技术可以使用分层聚类算法确定相册的一个或多个聚类，并根据一个或多个聚类存储相册。 该技术可以使用一个或多个聚类来控制相册的显示方式。 该技术可以基于用户输入来调整一个或多个聚类中的至少一个和自动相册的生成。 用户输入可以包括关于一个或多个聚类的添加，删除和移动照片中的至少一个。 该技术可以重新聚集，自动生成新的相册和/或调整演示文稿。